Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to commands or orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idar
    -0.16
    indre
    -0.16
    	Copyright
    -0.15
     Angiospermae
    -0.15
    cial
    -0.15
    lights
    -0.15
    æĤī
    -0.14
    üssen
    -0.14
    attice
    -0.14
    cia
    -0.14
    POSITIVE LOGITS
    ATORY
    0.26
    arin
    0.23
     Mand
    0.19
    ev
    0.19
    eb
    0.18
    olin
    0.18
    ala
    0.17
    itory
    0.16
     mand
    0.16
    åĭĻ
    0.16
    Act Density 0.008%

    No Known Activations